{"id":"https://openalex.org/W6948705011","doi":"https://doi.org/10.5281/zenodo.13318542","title":"The Unreasonable Ineffectiveness of Nucleus Sampling on Mitigating Text Memorization","display_name":"The Unreasonable Ineffectiveness of Nucleus Sampling on Mitigating Text Memorization","publication_year":2024,"publication_date":"2024-08-14","ids":{"openalex":"https://openalex.org/W6948705011","doi":"https://doi.org/10.5281/zenodo.13318542"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.13318542","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.13318542","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.13318542","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Borec, Luka","orcid":null},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Borec, Luka","raw_affiliation_strings":["University of Potsdam"],"affiliations":[{"raw_affiliation_string":"University of Potsdam","institution_ids":["https://openalex.org/I176453806"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sadler, Philipp","orcid":"https://orcid.org/0000-0001-8260-5481"},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sadler, Philipp","raw_affiliation_strings":["University of Potsdam"],"affiliations":[{"raw_affiliation_string":"University of Potsdam","institution_ids":["https://openalex.org/I176453806"]}]},{"author_position":"last","author":{"id":null,"display_name":"Schlangen, David","orcid":"https://orcid.org/0000-0002-2686-6887"},"institutions":[{"id":"https://openalex.org/I176453806","display_name":"University of Potsdam","ror":"https://ror.org/03bnmw459","country_code":"DE","type":"education","lineage":["https://openalex.org/I176453806"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Schlangen, David","raw_affiliation_strings":["University of Potsdam"],"affiliations":[{"raw_affiliation_string":"University of Potsdam","institution_ids":["https://openalex.org/I176453806"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I176453806"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.12610000371932983,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.12610000371932983,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10895","display_name":"Species Distribution and Climate Change","score":0.08860000222921371,"subfield":{"id":"https://openalex.org/subfields/2302","display_name":"Ecological Modeling"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.05790000036358833,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.9107000231742859},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6553000211715698},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5889999866485596},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5264000296592712},{"id":"https://openalex.org/keywords/nucleus","display_name":"Nucleus","score":0.45509999990463257},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.34299999475479126},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.323199987411499}],"concepts":[{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.9107000231742859},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6553000211715698},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5889999866485596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5572999715805054},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5264000296592712},{"id":"https://openalex.org/C2780723820","wikidata":"https://www.wikidata.org/wiki/Q1934178","display_name":"Nucleus","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44609999656677246},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3506999909877777},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3190999925136566},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.26969999074935913},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26739999651908875},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25839999318122864},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.13318542","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.13318542","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.13318542","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.13318542","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,76],"present":[1],"OpenMemText":[2],"a":[3,7],"diagnostic":[4,31],"dataset":[5],"with":[6,72],"known":[8],"distribution":[9],"of":[10,20,22,25,39,86,96],"duplicates":[11],"that":[12,78],"gives":[13],"us":[14],"some":[15],"control":[16],"over":[17],"the":[18,26,35,84,94,99],"likelihood":[19],"memorization":[21,37,87],"certain":[23],"parts":[24],"training":[27],"data.":[28],"Given":[29],"this":[30],"dataset,":[32],"we":[33],"analyse":[34],"text":[36,66],"behavior":[38],"large":[40],"language":[41],"models":[42],"(LLMs)":[43],"when":[44],"subjected":[45],"to":[46,58,93],"nucleus":[47,53,79],"sampling.":[48],"Stochastic":[49],"decoding":[50,74],"methods":[51],"like":[52],"sampling":[54,80],"are":[55,69],"typically":[56],"applied":[57],"overcome":[59],"issues":[60],"such":[61],"as":[62],"monotonous":[63],"and":[64],"repetitive":[65],"generation,":[67],"which":[68],"often":[70],"observed":[71],"maximization-based":[73],"techniques.":[75],"hypothesize":[77],"might":[81],"also":[82],"reduce":[83],"occurrence":[85],"patterns,":[88],"because":[89],"it":[90],"could":[91],"lead":[92],"selection":[95],"tokens":[97],"outside":[98],"memorized":[100],"sequence.":[101],"See":[102],"https://github.com/lukaborec/memorization-nucleus-sampling":[103],"for":[104],"more":[105],"information.":[106]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}